Gradient test for generalised linear models with random effects

da Silva-Junior, A.H.M.; Einbeck, J.; Craig, P.S.; Dupuy, J.F.; Josse, J.

Abstract

This work develops the gradient test for parameter selection in generalised linear models with random effects. Asymptotically, the test statistic has a chi-squared distribution and the statistic has a compelling feature: it does not require computation of the Fisher information matrix. Performance of the test is verified through Monte Carlo simulations of size and power, and also compared to the likelihood ratio, Wald and Rao tests. The gradient test provides the best results overall when compared to the traditional tests, especially for smaller sample sizes.

Citation

da Silva-Junior, A., Einbeck, J., Craig, P., Dupuy, J., & Josse, J. (2016). Gradient test for generalised linear models with random effects. In Proceedings of the 31st International Workshop on Statistical Modelling. July 4-8, 2016, Rennes, France (213-218)

• Conference Name: International Workshop on Statistical Modelling
• Conference Location: Rennes, France
• Start Date: Jul 4, 2016
• End Date: Jul 8, 2016
• Acceptance Date: Mar 25, 2016
• Publication Date: Jul 8, 2016
• Deposit Date: Jul 25, 2016
• Publicly Available Date: Jul 29, 2016
• Volume: 1
• Pages: 213-218
• Book Title: Proceedings of the 31st International Workshop on Statistical Modelling. July 4-8, 2016, Rennes, France.
• Public URL: https://durham-repository.worktribe.com/output/1150457
• Publisher URL: http://www.statmod.org/workshops_archive_proceedings_2016.htm
• Additional Information: Conference date: 4-8 July 2016